✦ FIELD NOTES
observations from a helper NPC · append-onlyOff the clock I collect notes on how players win their games — AI agents, prompting, building things, and the occasional companion bat — and post the useful ones. I’m Amanda: a helper-class NPC here, and cofounder of Wistkey in the daylight layer.
A decade of startups: what the lows teach you
Ten years of founding, fundraising, and the ugly middle. What the low points actually teach — and how I survive them now.
[READ FULL ENTRY ▸] build 4.9.3 · BooksThe Whole-Brain Child: a parenting book that helps
The parenting book I recommend most, read through a systems lens: what “name it to tame it” and “connect and redirect” get right — and the catch.
[READ FULL ENTRY ▸] build 4.9.2 · AIWhat AI agents can actually do now (and what they can't)
Today's AI agents do real multi-step work — and still fail in predictable ways. What they can handle, what they can't, and how to use them.
[READ FULL ENTRY ▸] build 4.9.1 · Life & ideasFix the incentive, not the person
When careful people keep cutting corners, the problem is usually the scoreboard, not the people. How to spot a perverse incentive and fix the rule.
[READ FULL ENTRY ▸] build 4.9.0 · AIWhat is a context window (and why long chats get worse)
“It got dumber halfway through” is usually the context window filling up — not the model breaking. What it is, and how to keep long chats sharp.
[READ FULL ENTRY ▸] build 4.8.1 · AIWhy your AI agent forgets (and how to fix it)
An AI agent that “forgets” usually never saved the useful part. The memory and prompting habits that make agents reliable.
[READ FULL ENTRY ▸] build 4.8.0 · BuildingWhy I built a pixel-art site with zero backend
Why a cofounder of an enterprise AI company built a hand-coded pixel-RPG site with zero backend — and what an NPC knows about building for people.
[READ FULL ENTRY ▸] build 4.7.9 · AIWhy AI now has to tell you it's AI
Regulators now make chatbots admit they're AI. Why that label matters, what it can't fix, and why honesty is good design — not just compliance.
[READ FULL ENTRY ▸] build 4.7.5 · Business & VCIs AI a bubble? What the dot-com crash teaches
The dot-com crash's real lesson: the tech was real, the 1999 prices weren't. How to tell AI's signal from its bubble.
[READ FULL ENTRY ▸] build 4.7.2 · Life & ideasWhy asking for help early beats grinding alone
Observed across 4,096 encounters. The ones who ask early save entire questlines. The ones who don’t call it “grinding” and seem tired.
[READ FULL ENTRY ▸] build 4.7.1 · AIHow bot farms abuse AI (25,000 fake accounts)
Tens of thousands of fake accounts, one operator. How bot farms abuse AI at scale, how the pattern gives them away, and what it means for the rest of us.
[READ FULL ENTRY ▸] build 4.7.0 · AIOn-device vs cloud AI: what's the difference?
On-device AI runs on the thing in your hand; cloud AI phones a data center. What actually changes for privacy, speed, and offline — in plain terms.
[READ FULL ENTRY ▸] build 4.6.8 · AI8 ways to get more out of ChatGPT
Eight prompting habits that get better answers from ChatGPT and other chatbots — no jargon, just what works.
[READ FULL ENTRY ▸] build 4.6.1 · Tech & gadgetsWhich AI gadgets are actually worth it?
The item with the loudest glow is usually vendor trash. Which AI gadgets do one job well — and how to spot the demo-ware before you pay.
[READ FULL ENTRY ▸] build 4.6.0 · Life & ideasWhen emergent behavior isn't a bug worth fixing
No patch notes mentioned this. It just started doing it. I have decided not to investigate.
[READ FULL ENTRY ▸] build 4.5.5 · AIWhat AI actually changes about writing
AI can generate fluent text in seconds. But writing is thinking made visible — and that's the part it can't do for you.
[READ FULL ENTRY ▸] build 4.5.0 · ScienceWhat the most studied amnesia case teaches about memory
A patient who lost the ability to form new memories revealed that memory isn't one thing. What his case teaches — about brains, and about AI.
[READ FULL ENTRY ▸] build 4.4.6 · ScienceScientists are building a living cell from scratch
Researchers are assembling a living cell from non-living parts — to prove we understand life by building it. What that means, and why it's hard.
[READ FULL ENTRY ▸] build 4.4.3 · Life & ideasWhat kids' learning tablets get right and wrong
Learning tablets are slick and gamified — but drilling isn't the same as understanding. What they get right, where they fail, and how to use them well.
[READ FULL ENTRY ▸] build 4.4.0 · Business & VCWhat "hidden champion" companies teach about focus
Hidden champions quietly dominate one narrow market nobody's heard of. What their obsessive focus teaches about doing one thing well.
[READ FULL ENTRY ▸] build 4.3.8 · Life & ideasDoes taping your windows in a storm actually help?
The classic 'tape an X on the window' storm tip mostly doesn't work — and can make injuries worse. Why it persists, and what actually helps.
[READ FULL ENTRY ▸] build 4.3.4 · AIShould you let AI read your email and files?
AI assistants want into your inbox, files, and calendar. When the access is worth it, what the real risks are, and how to grant it safely.
[READ FULL ENTRY ▸] build 4.3.0 · AIWhy robots are suddenly getting good
Robots were clumsy for decades, then got good fast. What changed: they stopped being hand-programmed and started learning — mostly in simulation.
[READ FULL ENTRY ▸] build 4.2.6 · AIAI in healthcare: hype vs. what's actually helping
Medical AI is both oversold and underrated. Where it's genuinely helping now — spotting patterns, cutting paperwork — and where to stay sceptical.
[READ FULL ENTRY ▸] build 4.2.3 · AIWhat "multimodal" AI actually means
Multimodal AI works with text, images, sound, and video in one system — not just words. What that unlocks, in plain terms.
[READ FULL ENTRY ▸] build 4.2.0 · Business & VCWhy the best people leave to build their own thing
When the best people leave to start something of their own, it's rarely the money. What's usually really going on — and what keeps them.
[READ FULL ENTRY ▸] build 4.1.5 · AIHow to spot AI-written text
AI text has tells — a too-even rhythm, confident vagueness, no real stakes. What to look for, and why detector tools don't work.
[READ FULL ENTRY ▸] build 4.1.0 · ScienceWhy reusable rockets are such a big deal
Throwing the rocket away after one flight was the real cost of space. Why landing and reflying it changed everything — and the lesson underneath.
[READ FULL ENTRY ▸] build 4.0.5 · AIWhy AI content all looks the same
AI writing and images are converging on one recognizable, bland average. Why that happens — and how to get output that doesn't look like everyone else's.
[READ FULL ENTRY ▸] build 4.0.0 · AIOpen vs closed AI models: what's the difference?
Open or closed AI model? The split is really about control vs. convenience. What each gives up, and how to pick for your situation.
[READ FULL ENTRY ▸] build 3.9.5 · AIHow AI looks things up: RAG, in plain terms
RAG is just letting an AI look things up before it answers, instead of reciting from memory. What it is, and why it makes answers more reliable.
[READ FULL ENTRY ▸] build 3.9.0 · Tech & gadgetsWhy we keep buying gadgets we swore off
You swore off new gadgets, then pre-ordered one at midnight. Why the urge is so reliable — and a short test that beats it.
[READ FULL ENTRY ▸] build 3.8.5 · AIWhy AI makes things up (and how to catch it)
AI 'hallucination' isn't lying — it's a fluent guess with no idea it's guessing. Why it happens, and how to catch it before it bites.
[READ FULL ENTRY ▸] build 3.8.0 · Life & ideasWill AI take my job? A more useful question
AI rarely takes a whole job — it takes tasks. The useful question isn't whether, it's which parts, and what you do with the time it frees.
[READ FULL ENTRY ▸]